Connected Autonomous Vehicles (CAVs) are expected to share the roads with Human Driven Vehicles for the foreseeable. The random sequences in this mixed traffic flow render the design of CAV controllers particularly challenging.
This project investigates the design of a deep reinforcement learning algorithm algorithms to reduce the training dimensions and alleviate computational burdens. This controller aims to improve mixed traffic safety, efficiency and stability under varying CAV penetration rates with different sequences of CAVs and HDVs and different string lengths.
References
Haotian Shi, Danjue Chen, Nan Zheng, Xin Wang, Yang Zhou, Bin Ran, “A deep reinforcement learning based distributed control strategy for connected automated vehicles in mixed traffic platoon”, Transportation Research Part C: Emerging Technologies, Volume 148, 2023. https://www.sciencedirect.com/science/article/pii/S0968090X23000086
Haotian Shi, Yang Zhou, Keshu Wu, Xin Wang, Yangxin Lin, Bin Ran, “Connected automated vehicle cooperative control with a deep reinforcement learning approach in a mixed traffic environment”, Transportation Research Part C: Emerging Technologies, Volume 133, 2021.